11 papers
BenchmarkAnything: Agent-Driven Construction of Simulator-Ready Microarchitecture Benchmarks
Xiangfeng Sun, Ceyu Xu, Chen Bai +1
The selection of benchmark workloads is of paramount importance in computer architecture, as it establishes the yardstick against which architectural innovations are measured and g…
YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech
William Chen, Shinnosuke Takamichi, Sayaka Shiota +3
We present YODAS v3, a weakly-labeled speech corpus containing over 1.1 million hours of 48kHz multi-channel audio in 147 languages, released under a CC BY 3.0 license. YODAS v3 is…
Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens
Daigo Takizawa, Tomohiko Nakamura, Samuele Cornell +3
Neural audio codecs (NACs) have become popular for obtaining speech representations as discrete tokens. Beyond compression, discrete tokens can be used to train self-supervised lea…
UT-AISTimprt submission for ICME 2026 Grand Challenge on Academic Text-to-Music Generation
Shunsuke Yoshida, Yu-Hua Chen, Satoru Fukayama
This work investigates the effect of batch sampling strategies during training for text-to-audio music generation under low-data and small-scale model settings. This paper describe…
The CMU-AIST submission for the ICME 2025 Audio Encoder Challenge
Shikhar Bharadwaj, Samuele Cornell, Kwanghee Choi +4
This technical report describes our submission to the ICME 2025 audio encoder challenge. Our submitted system is built on BEATs, a masked speech token prediction based audio encode…
Voice Conversion for Likability Control via Automated Rating of Speech Synthesis Corpora
Hitoshi Suda, Shinnosuke Takamichi, Satoru Fukayama
Perceived voice likability plays a crucial role in various social interactions, such as partner selection and advertising. A system that provides reference likable voice samples ta…
IdolSongsJp Corpus: A Multi-Singer Song Corpus in the Style of Japanese Idol Groups
Hitoshi Suda, Junya Koguchi, Shunsuke Yoshida +3
Japanese idol groups, comprising performers known as "idols," are an indispensable part of Japanese pop culture. They frequently appear in live concerts and television programs, en…
OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder
Shikhar Bharadwaj, Samuele Cornell, Kwanghee Choi +4
Masked token prediction has emerged as a powerful pre-training objective across language, vision, and speech, offering the potential to unify these diverse modalities through a sin…
Discrete Speech Unit Extraction via Independent Component Analysis
Tomohiko Nakamura, Kwanghee Choi, Keigo Hojo +3
Self-supervised speech models (S3Ms) have become a common tool for the speech processing community, leveraging representations for downstream tasks. Clustering S3M representations…
FruitsMusic: A Real-World Corpus of Japanese Idol-Group Songs
Hitoshi Suda, Shunsuke Yoshida, Tomohiko Nakamura +2
This study presents FruitsMusic, a metadata corpus of Japanese idol-group songs in the real world, precisely annotated with who sings what and when. Japanese idol-group songs, vita…
Self-Supervised Speech Representations are More Phonetic than Semantic
Kwanghee Choi, Ankita Pasad, Tomohiko Nakamura +3
Self-supervised speech models (S3Ms) have become an effective backbone for speech applications. Various analyses suggest that S3Ms encode linguistic properties. In this work, we se…